Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for establishing cross-language information, comprising: collecting a plurality of object information sets from a plurality of network platforms by a processor of a system; by the processor, building a first data structure corresponding to a source language and a second data structure corresponding to a target language according to the plurality of object information sets, wherein the plurality of object information sets is composed of a plurality of first object information sets and a plurality of second object information sets, characteristic data of the plurality of first object information sets comprises a plurality of pieces of first image data and a plurality of pieces of first hashtag data, and characteristic data of the plurality of second object information sets comprises a plurality of pieces of second image data and a plurality of pieces of second hashtag data; by the processor, performing an image-classification task for the plurality of first object information sets according to the plurality of pieces of first image data to form a plurality of source image groups, wherein the plurality of first object information sets in each of the plurality of source image groups have identical first image characteristics; and by the processor, performing the image-classification task for the plurality of second object information sets according to the plurality of pieces of second image data to form a plurality of target image groups, wherein the plurality of second object information sets in each of the plurality of target image groups have identical second image characteristics; wherein each of the plurality of source image groups comprises a plurality of source hashtag groups, and each of the plurality of target image groups comprises a plurality of target hashtag groups.
2. The method for establishing cross-language information according to claim 1 , further comprising: by the processor, performing a hashtag-classification task for the plurality of first object information sets in each of the plurality of source image groups according to the plurality of pieces of first hashtag data to form the plurality of source hashtag groups, wherein the plurality of first object information sets in each of the plurality of source hashtag groups have identical first hashtag characteristics.
3. The method for establishing cross-language information according to claim 1 , further comprising: by the processor, performing a hashtag-classification task for the plurality of second object information sets in each of the plurality of target image groups according to the plurality of pieces of second hashtag data to form the plurality of target hashtag groups, wherein the plurality of second object information sets in each of the plurality of target hashtag groups have identical second hashtag characteristics.
4. A method for processing cross-language information, comprising: collecting a plurality of object information sets from a plurality of network platforms by a processor of a system; by the processor, establishing a first data structure corresponding to a source language and a second data structure corresponding to a target language according to a plurality of object information sets, wherein the plurality of object information sets is composed of a plurality of first object information sets and a plurality of second object information sets, characteristic data of the plurality of first object information sets comprises a plurality of pieces of first image data and a plurality of pieces of first hashtag data, and characteristic data of the plurality of second object information sets comprises a plurality of pieces of second image data and a plurality of pieces of second hashtag data; by the processor, performing an image-classification task for the plurality of first object information sets according to the plurality of pieces of first image data to form a plurality of source image groups, wherein the plurality of first object information sets in each of the plurality of source image groups have identical first image characteristics; and by the processor, performing the image-classification task for the plurality of second object information sets according to the plurality of pieces of second image data to form a plurality of target image groups, wherein the plurality of second object information sets in each of the plurality of target image groups have identical second image characteristics; by an operation interface of a system, receiving a set of target object information, and by the processor, capturing characteristic data of the set of target object information; by the processor, selecting a first related image group from the first data structure corresponding to the source language according to the characteristic data of the set of target object information captured; by the processor, performing a cross-language comparison task according to the first related image group to select a second related image group; by the operation interface, displaying a plurality of candidate object images according to the second related image group; and by the processor, selecting one of the plurality of candidate object images as a final target object image according to a user command; wherein the characteristic data of the set of target object information comprises an image characteristic and a hashtag characteristic.
5. The method for processing cross-language information according to claim 4 , wherein by the processor, selecting the first related image group from the first data structure corresponding to the source language according to the characteristic data of the set of target object information captured comprising: by the processor, selecting one of the plurality of source image groups in the first data structure as the first related image group, wherein a first image characteristic of the source image group selected matches the image characteristic of the set of target object information.
6. The method for processing cross-language information according to claim 5 , wherein the cross-language comparison task comprising: by the processor, selecting one of the plurality of target image groups in the second data structure corresponding to the target language as the second related image group according to the first image characteristic of the source image group serving as the first related image group, wherein a second image characteristic of the target image group selected matches the first image characteristic of the source image group selected.
7. The method for processing cross-language information according to claim 4 , further comprising: by the processor, performing a hashtag-classification task according to a plurality of pieces of first hashtag data of the plurality of first object information sets in each of the plurality of source image groups to form a plurality of source hashtag groups, wherein the plurality of first object information sets in each of the plurality of source hashtag groups have identical first hashtag characteristics.
8. The method for processing cross-language information according to claim 4 , further: by the processor, performing a hashtag-classification task according to a plurality of pieces of second hashtag data of the plurality of second object information sets in each of the plurality of target image groups to form a plurality of target hashtag groups, wherein the plurality of second object information sets in each of the plurality of target hashtag groups have identical second hashtag characteristics.
9. The method for processing cross-language information according to claim 4 , further comprising: by the processor, receiving a user feedback score related to the candidate object image selected.
10. The method for processing cross-language information according to claim 9 , further comprising: by the processor, adjusting a ranking of the plurality of candidate objects according to the user feedback score.
11. A cross-language information system, adapted to a plurality of network platforms, the cross-language information system comprising: a database configured to store a first data structure corresponding to a source language and a second data structure corresponding to a target language; an operation interface configured to receive a set of target object information; a hardware processor connected to the database and the operation interface, with the processor configured to capture characteristic data of the set of target object information and select a first related image group from the first data structure corresponding to the source language according to the characteristic data of the set of target object information captured, the hardware processor configured to perform a cross-language comparison task according to the first related image group to select a second related image group and control the operation interface to display a plurality of candidate object images according to the second related image group, the processor further configured to select one of the plurality of candidate object images as a final target object image according to a user command; wherein the characteristic data of the set of target object information comprises an image characteristic and a hashtag characteristic; wherein the hardware processor forms a plurality of source image groups by performing an image-classification task for a plurality of first object information sets in the first data structure according to a plurality of pieces of first image data of the plurality of first object information sets, wherein the plurality of first object information sets in each of the plurality of source image groups have identical the first image characteristics, the hardware processor forms a plurality of target image groups by performing the image-classification task for a plurality of second object information sets in the second data structure according to a plurality of pieces of second image data of the plurality of second object information sets, wherein the plurality of second object information sets in each of the plurality of target image groups have identical the second image characteristics.
12. The cross-language information system according to claim 11 , wherein the first related image group is one of the plurality of source image groups, which is selected by the hardware processor from the first data structure, and a first image characteristic of the source image group selected matches the image characteristic of the set of target object information.
13. The cross-language information system according to claim 12 , wherein the cross-language comparison task comprises: the hardware processor selects one of the plurality of target image groups in the second data structure corresponding to the target language as the second related image group according to the first image characteristic of the source image group serving as the first related image group, wherein a second image characteristic of the target image group selected matches the first image characteristic of the source image group selected.
14. The cross-language information system according to claim 11 , wherein the hardware processor is further configured to perform a hashtag-classification task to form a plurality of target hashtag groups according to a plurality of second hashtag information sets of the plurality of second object information sets in each of the plurality of target image groups, wherein the plurality of second object information sets in each of the plurality of target hashtag groups have identical second hashtag characteristics.
15. The cross-language information system according to claim 11 , wherein the hardware processor is further configured to perform a hashtag-classification task to form a plurality of source hashtag groups according to a plurality of first hashtag information sets of the plurality of first object information sets in each of the plurality of source image groups, wherein the plurality of first object information sets in each of the plurality of source hashtag groups have identical first hashtag characteristics.
16. The cross-language information system according to claim 11 , wherein the operation interface is further configured to receive a user feedback score related to the candidate object image selected.
17. The cross-language information system according to claim 16 , wherein the hardware processor is further configured to adjust a ranking of the plurality of candidate object images according to the user feedback score.
Unknown
March 23, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.